© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31688
    Prev
    Next
    INDEX
    Explanations

    I am the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     my
    -0.14
     ours
    -0.12
    my
    -0.12
     our
    -0.12
    ffb
    -0.11
     Gre
    -0.11
    edo
    -0.11
     brav
    -0.11
    (my
    -0.11
     Ire
    -0.11
    POSITIVE LOGITS
     proud
    0.10
     nobody
    0.08
     wal
    0.08
     proudly
    0.08
     Proud
    0.08
    öl
    0.08
    /we
    0.08
    Disclaimer
    0.08
     disclaimer
    0.08
     fl
    0.07
    Activations Density 0.121%

    No Known Activations